Agentic AI for Engineering Leaders | Strategy & Execution Guide
summary
Explains how retrieval-augmented generation pairs vector DB embeddings and chunked corporate docs so LLMs return domain-precise answers, and how MCP tools (GitHub, Confluence, Jira examples) let agents perform CRUD and orchestrate multi-step workflows; outlines multi-agent patterns — centralized supervisor, skill-based specialists, router-style agents — and recommends human-in-the-loop for high-risk writes, observability and governance, cites vendor frameworks (Microsoft agent framework, AWS Bedrock) and a claimed ~40% adoption signal for agentic workflows.
AI-written summary · about
chapters (9)
- 0:00Agentic AI introduction
- 1:14What is agentic AI
- 3:19Agentic AI trends 2024
- 5:03Retrieval augmented generation
- 8:33Model context protocol
- 13:55Multi-agent design patterns
- 17:25Implementation frameworks
- 19:49Human-in-the-loop risks
- 20:53Path forward adoption
related talks
27mAgentic Engineering: Working With AI, Not Just Using It
40mAgentic AI: The Next Evolution of Automation
29mBuilding Trust in AI Agents
28mAgentic AI
28mAgentic Enterprise - What your CEO must know about AI
31mAgentic AI architecture patterns
22mHOW TO BUILD YOUR OWN AI AGENT: THE COMPLETE ARCHITECTURE FOR ENGINEERING TEAMS
33mAsk Me Anything: AI Agents, Skills, Career & Growth